Detection system and detection method of PCB (Printed Circuit Board)

Abstract

The invention discloses a detection system of a PCB (Printed Circuit Board). The detection system comprises PCB detection equipment, a data storage module and analysis and test equipment, the PCB detection equipment is used for acquiring current detection data of a to-be-detected PCB according to a preset detection index of the PCB and uploading the current detection data to the data storage module; the preset detection indexes of the PCB comprise the types and the number of the components, the positions and the resistance directions of the preset components, the plugging directions of the direct plugging components, the welding spots of the components and the board surface of the PCB; the data storage module is used for storing current test data, historical test data of the PCB, scoring standards and scores; the analysis test equipment comprises an abnormality diagnosis module used for determining the current abnormal data of the PCB to be tested according to the current test data; and the scoring module is used for obtaining the score of the tested PCB according to the current abnormal data and the scoring standard, so that the detection of the PCB can be automatically completed.

Description

Technical Field

[0001] The present application relates to the technical field of circuit boards, and in particular to a detection system and a detection method for a PCB board. Background Art

[0002] With the continuous development of industrial automation technology, the global machine vision market is growing rapidly, and the domestic market will reach a scale of tens of billions. Machine vision is not only increasingly used in the industrial field, but is also widely used in competitions and teaching. In the electronic technology project competition of the World Skills Competition, contestants need to test the following contents: the total number of components and the corresponding positions, the determination of the direction of resistors, whether the plug-in components are skewed, the quality of component solder joints, the cleanliness of circuit boards, and many other contents. After the contestants soldered the above components to the PCB, the referees still used manual grouping to judge and score the quality of PCB soldering. The judging time was long and there were inconsistent standards. It was too subjective, which became the most controversial judging item in the electronic technology project competition of previous World Skills Competitions. Summary of the invention

[0003] The present application provides a PCB board detection system and detection method, which automatically completes the detection of PCB boards to shorten the evaluation time and make the scoring standard more objective and unified.

[0004] In order to solve the above technical problems, in a first aspect, the present application provides a PCB board detection system, including a PCB board detection device, a data storage module and an analysis and testing device; The PCB board detection device is used to obtain current detection data of the PCB board to be tested according to the preset detection indicators of the PCB board, and upload the current detection data to the data storage module; the preset detection indicators of the PCB board include the type and quantity of components, the position of preset components, the direction of resistance, the plug-in direction of direct-insert components, the solder joints of components, and the board surface of the PCB board; The data storage module is used to store the current test data, historical test data of the PCB board, scoring criteria and scores; The analytical testing equipment comprises: An abnormality diagnosis module, used for determining the current abnormality data of the PCB board to be tested according to the current test data; The scoring module is used to obtain a scoring score of the tested PCB board according to the current abnormal data and the scoring standard.

[0005] In some embodiments, the PCB board detection device includes: Visual platform, used to place the PCB board to be tested; An industrial camera, wherein the industrial camera has a lens, and is used to obtain current detection data of the PCB board to be tested and upload the current detection data to the data storage module; The light source is used to provide illumination for the PCB board to be tested.

[0006] In some of the embodiments, the abnormality diagnosis module includes: Component detection unit, used to identify whether the type and quantity of components on the PCB board are abnormal; Component position detection unit, used to detect whether the position of the preset components on the PCB is correct; The resistor direction detection unit is used to identify whether the resistor on the PCB is installed in the wrong direction; The plug-in direction detection unit for plug-in components is used to identify whether the plug-in components on the PCB are tilted and whether the surface is damaged; Component solder joint detection unit, used to identify whether the component solder joints on the PCB meet the welding requirements; The PCB board surface detection unit is used to detect whether there are scratches on the surface of the PCB board.

[0007] In a second aspect, the present application also includes a PCB board detection method, which is applied to the detection method in the PCB board detection system, and the method includes: Place the PCB to be tested on the visual platform; The imaging graphic information of the PCB board to be tested is obtained through the lens of the industrial camera and sent to the abnormal diagnosis module; The component detection unit identifies the types and quantities of abnormal components on the PCB board, and sends the abnormal component information to the scoring module; Detecting the preset components with soldering position deviation on the PCB board through the component position detection unit, and sending the preset component information with position deviation to the scoring module; Identify the reverse installed resistors on the PCB board through the resistor direction detection unit, and send the reverse installed resistor information to the scoring module; Identify through-hole components with tilted insertion and damaged surfaces on the PCB through a through-hole component insertion direction detection unit, and send information on the tilted insertion and damaged surfaces of the through-hole components to a scoring module; Identify abnormal solder joints of components on the PCB board through the component solder joint detection unit, and send the abnormal solder joint information to the scoring module; Identify scratches on the surface of the PCB board through the board surface detection unit of the PCB board, and send the scratch information on the surface of the PCB board to the scoring module; The scoring module compares the acquired abnormal component information, reverse installed resistor information, plug-in component tilt and surface damage information, abnormal solder joint information, and PCB surface scratch information with the preset scoring criteria to obtain a comprehensive score for the tested PCB board.

[0008] In some of the embodiments, the method of identifying the types and quantities of abnormal components of the PCB board by the component detection unit is: Position the PCB board to be tested through the positioning holes; Define fixed ROIs for various types of components; Create different component template libraries through multi-template matching algorithm; Obtain the number of components in different template libraries and compare them with the preset number; Determine whether the types and quantities of components soldered on the PCB are missing.

[0009] In some of the embodiments, the method for detecting the preset components with soldering position deviation on the PCB is: Position the PCB board to be tested through the positioning holes; Set the preset component template through the template matching algorithm; After locating the preset component, find the coordinates of the intersection of the two sides of the preset component; Compare the difference between the intersection coordinates and the PCB center coordinates to see if they are the same as the preset difference; If yes, there is no offset in the preset component welding position.

[0010] In some of the embodiments, the method for identifying reversely installed resistors on a PCB is: Position the PCB board to be tested through the positioning holes; Locate all resistor locations through deep learning detection algorithms; A deep learning classification algorithm is used to extract the resistor color ring features; The image classification network is used to determine whether the resistor orientation is correct.

[0011] In some embodiments, the method for identifying the plug-in components with tilted insertion and damaged surfaces on the PCB is as follows: Position the PCB board to be tested through the positioning holes; Define a fixed ROI for plug-in components; An unsupervised algorithm is used to detect whether the plug-in components are skewed; A segmentation algorithm is used to detect whether the surface of the plug-in components is damaged.

[0012] In some embodiments, the method for identifying abnormal solder joints of components on a PCB is: Position the PCB board to be tested through the positioning holes; The solder joint features can be highlighted through color space conversion; The position of the solder joint can be located through coarse positioning; By judging the position, it can be determined whether the solder joint is missing or misplaced; Cut the pin solder joints of the components and send them to the deep learning classification network; The confidence level is used to determine whether the solder joint is full, whether there is insufficient tin, or whether there is a tin tip.

[0013] In a third aspect, the present application also provides a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the PCB board detection method is implemented.

[0014] Compared with the prior art, this application has at least the following beneficial effects: The present application uses a PCB board detection system to place the PCB board to be tested on a visual platform, obtains imaging graphic information of the PCB board to be tested through the lens of an industrial camera and sends it to an abnormal diagnosis module, identifies the type and number of abnormal components on the PCB board through a component detection unit, and sends the abnormal component information formed to a scoring module. The component position detection unit is used to detect preset components with offset welding positions on the PCB board, and sends the preset component information of the offset position to the scoring module, identifies reversed resistors on the PCB board through a resistor direction detection unit, and sends the reversed resistor information to the scoring module, and identifies plug-in tilt and surface damage on the PCB board through a plug-in component plug-in direction detection unit. The through-hole components are detected, and the information of the through-hole component connection tilt and surface damage is sent to the scoring module. The abnormal solder joints of the components on the PCB board are identified through the component solder joint detection unit, and the abnormal solder joint information is sent to the scoring module. The surface scratches of the PCB board are identified through the board surface detection unit of the PCB board, and the surface scratch information of the PCB board is sent to the scoring module. The scoring module compares the acquired abnormal component information, reverse resistance information, through-hole component connection tilt and surface damage information, abnormal solder joint information, and PCB board surface scratch information with the preset scoring standard to obtain a comprehensive score of the tested PCB board. The entire scoring process is automatically completed by the system, which shortens the judging time and makes the scoring standard more objective and unified. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the structure of a PCB board detection system shown in an embodiment of the present application; Figure 2 A schematic diagram of a circuit board testing method according to an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computer device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] Please refer to Figure 1 , the present application provides a PCB board detection system, including a PCB board detection device 1, a data storage module 2 and an analysis and testing device 3; The PCB board detection device 1 is used to obtain current detection data of the PCB board to be tested according to the preset detection indicators of the PCB board, and upload the current detection data to the data storage module 2; the preset detection indicators of the PCB board include the type and quantity of components, the position of preset components, the direction of resistance, the plug-in direction and appearance of direct-insert components, the solder joints of components, and the board surface of the PCB board; The data storage module 2 is used to store the current test data, historical test data of the PCB board, scoring criteria and scores; The analysis and testing equipment 3 comprises: The abnormality diagnosis module 31 is used to determine the current abnormality data of the PCB board to be tested according to the current test data; The scoring module 32 is used to obtain a scoring score of the tested PCB board according to the current abnormal data and the scoring standard.

[0018] The PCB board detection equipment comprises: Visual platform, used to place the PCB board to be tested; An industrial camera, wherein the industrial camera has a lens, and is used to obtain current detection data of the PCB board to be tested and upload the current detection data to the data storage module; The light source is used to provide illumination for the PCB board to be tested.

[0019] In some of the embodiments, the abnormality diagnosis module includes: Component detection unit, used to identify whether the type and quantity of components on the PCB board are abnormal; Component position detection unit, used to detect whether the position of the preset components on the PCB is correct; The resistor direction detection unit is used to identify whether the resistor on the PCB is installed in the wrong direction; The plug-in direction detection unit for plug-in components is used to identify whether the plug-in components on the PCB are tilted and whether the surface is damaged; Component solder joint detection unit, used to identify whether the component solder joints on the PCB meet the welding requirements; The PCB board surface detection unit is used to detect whether there are scratches on the surface of the PCB board.

[0020] When testing a PCB board, first place the PCB board to be tested on the visual platform. The industrial camera is slidably fitted on the support column of the visual platform. It can slide in the vertical direction on the support column of the visual platform, and then approach or move away from the PCB board to be tested. The light source is started to illuminate the PCB board to be tested. The lens is moved to a preset position by the industrial camera to take a picture of the PCB board to obtain image information of the front and back of the PCB board, and the image information is sent to the data storage module 2 and the abnormality diagnosis module 31 in the analysis and testing equipment 3 respectively.

[0021] The component detection unit identifies the types and quantities of abnormal components on the PCB board, and sends the abnormal component information to the scoring module. The component position detection unit detects the preset components with soldering position deviation on the PCB board, and sends the preset component information of position deviation to the scoring module. The resistor direction detection unit identifies the reverse resistor on the PCB board, and sends the reverse resistor information to the scoring module. The plug-in component connection direction detection unit identifies the plug-in tilted and surface damaged plug-in components on the PCB board, and sends the plug-in tilted and surface damaged plug-in component information to the scoring module. The device solder joint detection unit identifies abnormal solder joints of components on the PCB board and sends the abnormal solder joint information to the scoring module. The PCB board surface detection unit identifies scratches on the PCB board surface and sends the PCB board surface scratch information to the scoring module. The scoring module compares the acquired abnormal component information, reversed resistor information, plug-in component tilt and surface damage information, abnormal solder joint information, and PCB board surface scratch information with the preset scoring criteria. For example, if the total score is 100 points, then 0.3 points will be deducted for a missing resistor and 0.2 points will be deducted for a reversed resistor. Finally, the score of the tested PCB board is obtained.

[0022] In this way, the present application uses a PCB board detection system to place the PCB board to be tested on a visual platform, obtains imaging graphic information of the PCB board to be tested through the lens on the industrial camera and sends it to the abnormal diagnosis module, identifies the type and quantity of abnormal components on the PCB board through the component detection unit, and sends the abnormal component information to the scoring module. The component position detection unit is used to detect preset components with offset welding positions on the PCB board, and sends the preset component information of the offset position to the scoring module, identifies the reversed resistors on the PCB board through the resistor direction detection unit, and sends the reversed resistor information to the scoring module, and identifies the plug-in inclination and surface of the PCB board through the plug-in component plug-in direction detection unit. The damaged plug-in components are detected, and the plug-in component tilting and surface damage information is sent to the scoring module. The abnormal solder joints of the components on the PCB board are identified by the component solder joint detection unit, and the abnormal solder joint information is sent to the scoring module. The surface scratches of the PCB board are identified by the board surface detection unit of the PCB board, and the surface scratch information of the PCB board is sent to the scoring module. The scoring module compares the acquired abnormal component information, reverse resistor information, plug-in component tilting and surface damage information, abnormal solder joint information, and PCB board surface scratch information with the preset scoring standards to obtain a comprehensive score for the tested PCB board. The entire scoring process is automatically completed by the system, which shortens the judging time and makes the scoring standards more objective and unified.

[0023] Please refer to Figure 2 In a second aspect, the present application further includes a PCB board detection method, which is applied to the detection method in the PCB board detection system, and the method includes: S1. Place the PCB to be tested on the visual platform; S2, obtaining the imaging graphic information of the PCB board to be tested through the lens of the industrial camera and sending it to the abnormal diagnosis module; S3, identifying the types and quantities of abnormal components on the PCB board through the component detection unit, and sending the abnormal component information to the scoring module; S4, detecting preset components with soldering position shift on the PCB board by a component position detection unit, and sending information of the preset components with position shift to a scoring module; S5, identifying the reverse-installed resistors on the PCB board through the resistor direction detection unit, and sending the reverse-installed resistor information to the scoring module; S6, identifying through-hole components with tilted insertion and damaged surfaces on the PCB board through the through-hole component insertion direction detection unit, and sending the through-hole component insertion tilt and surface damage information to the scoring module; S7, identifying abnormal solder joints of components on the PCB board through the component solder joint detection unit, and sending the abnormal solder joint information to the scoring module; S8, identifying scratches on the surface of the PCB board through the board surface detection unit of the PCB board, and sending the scratch information on the surface of the PCB board to the scoring module; S9. The scoring module compares the acquired abnormal component information, reverse resistor information, plug-in component tilt and surface damage information, abnormal solder joint information, and PCB board surface scratch information with the preset scoring standard to obtain the scoring score of the tested PCB board.

[0024] In some of the embodiments, the method of identifying the types and quantities of abnormal components of the PCB board by the component detection unit is: S31, positioning the PCB board to be tested through the positioning holes; S32, defining fixed ROIs for various types of components; for example, resistors are divided into fixed ROIs, capacitors are divided into fixed ROIs, and the ROI is an image area selected from the PCB board; S33. Create a template library of different components through a multi-template matching algorithm; the multi-template matching algorithm is a pattern recognition technology that is used to find the template that best matches the input data in a set of templates. This technology is widely used in image processing, computer vision, pattern recognition and other fields. The basic idea of ​​multi-template matching is to compare the input data with a set of pre-defined templates to find the template that is most similar to the input data. Each template represents a category. In this way, multi-template matching can be used to solve multi-category pattern recognition problems. That is, templates of different components can be created, and the components identified by the image can be compared with the templates; S34, obtaining the number of components in different template libraries and comparing them with the preset number; S35. Determine whether the types and quantities of components soldered on the PCB are missing.

[0025] In some of the embodiments, the method for detecting the preset components with soldering position deviation on the PCB is: S41, positioning the PCB board to be tested through the positioning holes; S42, setting a preset component template through a template matching algorithm; S43, after locating the preset component, find the coordinates of the intersection points on both sides of the preset component; S44, comparing the difference between the intersection point coordinates and the PCB center point coordinates with a preset difference to see whether they are the same; S45. If yes, the preset component soldering position is not offset. The key components of the preset components refer to the core components in the entire circuit, such as the CPU that plays a controlling role, the power supply circuit that provides power, and the drive circuit that drives the load. They are often the components with the highest cost and are the focus of quality inspection. If the difference between the intersection coordinates and the center point coordinates of the PCB board is different, it is considered that the preset component soldering position is offset, and the corresponding score needs to be deducted.

[0026] In some of the embodiments, the method for identifying reversely installed resistors on a PCB is: S51, positioning the PCB board to be tested through the positioning holes; S52, locating all resistor positions through a deep learning detection algorithm; S53, extracting resistor color ring features using a deep learning classification algorithm; S54. Determine whether the direction of the resistor is correct through the image classification network.

[0027] Generally, the color of the last color ring of the resistor is used to determine whether the resistor is installed upside down. The last color ring of a general resistor usually uses gold, silver, and brown. However, gold, silver, and brown are basically not used in the first color ring of the resistor. Therefore, a deep learning classification algorithm is used to extract the resistor color ring features. If gold, silver, and brown are found in the first color ring of the resistor, it can be determined that the direction of the resistor is installed upside down, and the corresponding points need to be deducted.

[0028] In some embodiments, the method for identifying the plug-in components with tilted insertion and damaged surfaces on the PCB is as follows: S61, positioning the PCB board to be tested through the positioning holes; S62, define a fixed ROI for plug-in components; S63, using an unsupervised algorithm to detect whether the plug-in component is in a skewed state; S64. Use a segmentation algorithm to detect whether the surface of the plug-in component is damaged.

[0029] The unsupervised algorithm can determine whether the through-hole component is clear by the distance between the point outside the through-hole component and the point on the through-hole component on the same straight line. If the distance between the point outside the through-hole component and the corresponding point on the through-hole component changes, it is considered that the through-hole component is tilted and the corresponding score needs to be deducted.

[0030] The application of segmentation algorithms in surface damage detection mainly relies on image processing technology, which divides the image into multiple small areas (segments), each of which is called a "segment", and then analyzes the characteristics of these segments to detect damage. The key to this method is to identify damage by comparing the difference between each segment and the surrounding environment, which usually involves the following steps: ‌Preprocessing‌: includes image enhancement (such as denoising, contrast enhancement, etc.) and color space conversion to improve image quality and highlight damaged parts.

[0031] ‌Feature Extraction‌: Use edge detection algorithms (such as the Canny operator) and texture analysis to identify unique patterns of damaged areas, such as cracks or dents.

[0032] ‌Damage area localization‌: Determine the area that is most similar to the typical damage area through template matching or machine learning classification.

[0033] ‌Segmentation and thinning‌: Use region growing or clustering methods to gradually expand the damaged area, merge similar pixels, and use threshold segmentation to classify pixels into background or damaged areas.

[0034] ‌Post-processing‌: Remove false positive areas, i.e. irrelevant small false positive areas, and perform necessary repair or filling.

[0035] The effectiveness of this method depends on the meticulousness of image preprocessing, the accuracy of feature extraction, and the efficiency of the segmentation algorithm. Through these steps, the segmentation algorithm can effectively identify the damaged area from the complex background, providing a basis for subsequent repair or quality control.

[0036] In some embodiments, the method for identifying abnormal solder joints of components on a PCB is: S71, positioning the PCB board to be tested through the positioning holes; S72. Solder point features can be highlighted through color space conversion; S73, the position of the welding point can be located by rough positioning; S74. By position judgment, it can be determined whether the solder joint is missing or misplaced; S75, cutting the pin solder joints of the components and sending them to the deep learning classification network; S76. Use confidence level to determine whether the solder joint is full, whether there is insufficient tin, or whether there is a tin tip.

[0037] The features of solder joints can be highlighted through color space conversion, and then the position of solder joints can be located through coarse positioning. Position judgment can be used to determine whether the solder balls are missing or misplaced. By cutting the located solder joint areas for deep learning classification training, it can be concluded whether the solder joints meet the status through the color and morphology of the solder joints, and the solder joints that meet the requirements can be screened out through confidence.

[0038] Please refer to Figure 3 In a third aspect, the present application further provides a computer device 4, comprising a processor 40 and a memory 41, wherein the memory 41 is used to store a computer program 42, and when the computer program 42 is executed by the processor 40, the PCB board testing method is implemented.

[0039] The computer device 4 may be a computing device such as a tablet computer, a desktop computer, or a cloud server. The computer device may include but is not limited to a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 3 It is only an example of the computer device 4 and does not constitute a limitation on the computer device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0040] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0041] In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the computer device 4. The memory 41 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0042] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A PCB board detection system, characterized in that: Including PCB board testing equipment, data storage module and analysis and testing equipment; The PCB board detection device is used to obtain current detection data of the PCB board to be tested according to the preset detection indicators of the PCB board, and upload the current detection data to the data storage module; the preset detection indicators of the PCB board include the type and quantity of components, the position of preset components, the direction of resistance, the plug-in direction of direct-insert components, the solder joints of components, and the board surface of the PCB board; The data storage module is used to store the current test data, historical test data of the PCB board, scoring criteria and scores; The analytical testing equipment comprises: An abnormality diagnosis module, used for determining the current abnormality data of the PCB board to be tested according to the current test data; The scoring module is used to obtain a scoring score of the tested PCB board according to the current abnormal data and the scoring standard.

2. The PCB board detection system as claimed in claim 1, characterized in that: The PCB board detection equipment comprises: Visual platform, used to place the PCB board to be tested; An industrial camera, wherein the industrial camera has a lens, and is used to obtain current detection data of the PCB board to be tested and upload the current detection data to the data storage module; The light source is used to provide illumination for the PCB board to be tested.

3. The PCB board detection system as claimed in claim 1, characterized in that: The abnormality diagnosis module comprises: Component detection unit, used to identify whether the type and quantity of components on the PCB board are abnormal; Component position detection unit, used to detect whether the position of the preset components on the PCB is correct; The resistor direction detection unit is used to identify whether the resistor on the PCB is installed in the wrong direction; The plug-in direction detection unit for plug-in components is used to identify whether the plug-in components on the PCB are tilted and whether the surface is damaged; Component solder joint detection unit, used to identify whether the component solder joints on the PCB meet the welding requirements; The PCB board surface detection unit is used to detect whether there are scratches on the surface of the PCB board.

4. A method for detecting a PCB board, characterized in that: A detection method applied to a detection system for a PCB board as claimed in any one of claims 1 to 3, the method comprising: Place the PCB to be tested on the visual platform; The imaging graphic information of the PCB board to be tested is obtained through the lens of the industrial camera and sent to the abnormal diagnosis module; The component detection unit identifies the types and quantities of abnormal components on the PCB board, and sends the abnormal component information to the scoring module; Detecting the preset components with soldering position deviation on the PCB board through the component position detection unit, and sending the preset component information with position deviation to the scoring module; Identify the reverse installed resistors on the PCB board through the resistor direction detection unit, and send the reverse installed resistor information to the scoring module; Identify through-hole components with tilted insertion and damaged surfaces on the PCB through a through-hole component insertion direction detection unit, and send information on the tilted insertion and damaged surfaces of the through-hole components to a scoring module; Identify abnormal solder joints of components on the PCB board through the component solder joint detection unit, and send the abnormal solder joint information to the scoring module; Identify scratches on the surface of the PCB board through the board surface detection unit of the PCB board, and send the scratch information on the surface of the PCB board to the scoring module; The scoring module compares the acquired abnormal component information, reverse installed resistor information, plug-in component tilt and surface damage information, abnormal solder joint information, and PCB surface scratch information with the preset scoring criteria to obtain the scoring score of the tested PCB board.

5. The method for detecting a PCB board as claimed in claim 4, characterized in that: The method for identifying the types and quantities of abnormal components of a PCB board by a component detection unit is as follows: Position the PCB board to be tested through the positioning holes; Define fixed ROIs for various types of components; Create different component template libraries through multi-template matching algorithm; Obtain the number of components in different template libraries and compare them with the preset number; Determine whether the types and quantities of components soldered on the PCB are missing.

6. The method for detecting a PCB board as claimed in claim 4, characterized in that: The method for detecting the preset components of the soldering position deviation on the PCB board is: Position the PCB board to be tested through the positioning holes; Set the preset component template through the template matching algorithm; After locating the preset component, find the coordinates of the intersection of the two sides of the preset component; Compare the difference between the intersection coordinates and the PCB center coordinates to see if they are the same as the preset difference; If yes, there is no offset in the preset component welding position.

7. The method for detecting a PCB board as claimed in claim 4, characterized in that: The method for identifying the reversely installed resistor on the PCB board is: Position the PCB board to be tested through the positioning holes; Locate all resistor locations through deep learning detection algorithms; A deep learning classification algorithm is used to extract the resistor color ring features; The image classification network is used to determine whether the resistor orientation is correct.

8. The method for detecting a PCB board as claimed in claim 4, characterized in that: The method for identifying the plug-in components with tilted insertion and damaged surfaces on the PCB is as follows: Position the PCB board to be tested through the positioning holes; Define a fixed ROI for plug-in components; An unsupervised algorithm is used to detect whether the plug-in components are skewed; A segmentation algorithm is used to detect whether the surface of the plug-in components is damaged.

9. The method for detecting a PCB board as claimed in claim 4, characterized in that: The method for identifying abnormal solder joints of components on a PCB is as follows: Position the PCB board to be tested through the positioning holes; The solder joint features can be highlighted through color space conversion; The position of the solder joint can be located through coarse positioning; By judging the position, it can be determined whether the solder joint is missing or misplaced; Cut the pin solder joints of the components and send them to the deep learning classification network; The confidence level is used to determine whether the solder joint is full, whether there is insufficient tin, or whether there is a tin tip.

10. A computer device, characterized in that: It comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the PCB board detection method as described in any one of claims 4 to 8 is implemented.

Images